Get Rich Text Image URLs and Blob Data
// use reluctant regex to match each image tag individually
// https://docs.oracle.com/javase/tutorial/essential/regex/quant.html
Matcher imgMatcher = Pattern.compile( '<img(.+?)>' ).matcher( record.richTextField__c );
// iterate each image tag found
while ( imgMatcher.find() ) {
// get the image tag html
String imageTag = imgMatcher.group();
System.debug( 'imageTag=' + imageTag );
// get the value of the src attribute
// the leading space is significant to avoid other attributes like data-cke-saved-src
String imageURL = imageTag.substringBetween( ' src="', '"' );
System.debug( 'imageURL=' + imageURL );
// if url contained parameters they might be html escaped, unescape them
// or, more conservatively, replace '&' with '&'
String decodedURL = imageURL.unescapeHtml4();
System.debug( 'decodedURL=' + decodedURL );
// note, as of API 34.0 or later, getContent() is considered an http callout
// so take that into consideration for your unit tests and governor limits
// https://developer.salesforce.com/docs/atlas.en-us.pages.meta/pages/apex_System_PageReference_getContent.htm
PageReference page = new PageReference( decodedURL );
Blob b = page.getContent();
System.debug( 'blob=' + b );
System.debug( 'Enjoy your Blob, save it as a Document, ContentVersion, whatever!' );
System.debug(''); // I like blank lines in my logs, easier to scan/read =)
}
Link:
https://salesforce.stackexchange.com/questions/91692/get-images-from-rich-text-area-via-apex
